© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206274
    Prev
    Next
    INDEX
    Explanations

    porpoise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ق
    1.04
    ного
    1.00
    اد
    0.98
    ناها
    0.91
    ని
    0.89
    čius
    0.88
    น
    0.87
    ων
    0.85
    нда
    0.84
    cevam
    0.84
    POSITIVE LOGITS
     to
    1.48
     e
    1.32
     you
    1.12
     on
    1.10
     c
    1.09
     l
    1.05
     be
    1.05
     o
    1.05
     one
    1.04
     p
    1.02
    Activations Density 0.000%

    No Known Activations